MatterSpace Docs
Material discovery documentation.
Use these docs when the job is material discovery under real physical constraints and the cost of invalid candidate work is dominating the workflow.
Overview
What is MatterSpace?
MatterSpace is Vareon's material discovery product. It generates candidate material from property targets and hard constraints instead of relying on large propose-then-filter queues.
MatterSpace covers material and energy workflows: batteries, catalysts, coatings, electrolytes, superconductors, magnets, and related programs.
Use it when the problem is not a lack of candidate volume, but the difficulty of finding candidates that remain worth evaluating after real physical constraints show up.
Product Overview
- Material and energy workflows
- Constraint-aware candidate generation
- Campaigns for discovery, refinement, and benchmarks
- Blind rediscovery benchmark evidence
What Teams Get
- Candidate sets worth ranking or simulating
- Trade-offs surfaced earlier in the workflow
- A clearer link between targets, constraints, and campaign output
- A practical starting point for follow-on evaluation
Supported Workflows
Material programs MatterSpace is built to support.
Material and energy design problems that benefit from constraint-aware generation and disciplined candidate shortlisting.
Battery cathodes and energy storage
Catalysis and chemical processing
Solid-state electrolytes
Superconductors and quantum material
Photovoltaics and solar energy
Thermoelectrics and waste heat recovery
High-entropy alloys
Magnets and magnetic material
Coatings and surface engineering
Metamaterials and MOFs
Polymer design
Generation Workflow
From target specification to candidate shortlist.
MatterSpace keeps the candidate search aligned to the real program constraints instead of treating feasibility as a late-stage cleanup step.
Set the material objective
Describe the property targets, constraints, exclusions, and operating conditions that define a successful run.
Generate under constraints
MatterSpace searches composition and structure while keeping declared feasibility rules active during the campaign.
Compare trade-offs
Candidates are returned as sets worth ranking rather than a single answer detached from the rest of the frontier.
Choose the next evaluation path
Take the shortlist into simulation, lab planning, or a follow-on campaign with tighter constraints.
Campaign Modes
Choose the campaign mode by the job.
The public campaign model is straightforward: broad search, focused refinement, guided validation, or blind benchmark evaluation.
Open Discovery
Use when the program needs new material directions and there is no trusted starting point.
Prototype Optimization
Use when a known material is promising and the job is to improve it without reopening the full search space.
Guided Rediscovery
Use when prior internal or public material knowledge should steer the campaign while keeping evaluation disciplined.
Blind Rediscovery Benchmark
Use when the target must remain hidden until evaluation so the result tests independent recovery rather than target-conditioned search.
Early Testing
Programmatic access is scoped with evaluation partners.
MatterSpace integration paths are opened as part of a defined evaluation path rather than a broad self-serve surface.
API Reference
Early TestingProgrammatic access is staged with evaluation partners as workflow scope, constraints, and review requirements are finalized.
Python Workflows
Early TestingTeams integrating MatterSpace into internal research tooling can scope notebook and batch-job usage during evaluation.
Agent Access
Early TestingStructured integration paths are available where agent-driven workflows are part of the evaluation boundary.
Ready to scope a material discovery evaluation?
We can map your constraints, candidate requirements, and review path to the right MatterSpace evaluation setup.
MatterSpace is patent pending in the United States and other countries. Vareon, Inc.